Testing the performance of image representations for mass classification in digital mammograms

Angelini, Enrico ; Campanini, Renato ; Iampieri, Emiro ; Lanconelli, Nico ; Masotti, Matteo ; Roffilli, Matteo (2004) Testing the performance of image representations for mass classification in digital mammograms. [Preprint]
Avviso

Esiste un'altra versione di questo documento. Clicca qui per vederla.

Full text disponibile come:
[thumbnail of masotti2004Testing.pdf]
Anteprima
Documento PDF
Download (219kB) | Anteprima

Abstract

In this paper a two-class classification problem is faced. One class is constituted by tumoral masses, breast tumors with size ranging from 3 mm to 30 mm. The other class is constituted by non-masses. A Support Vector Machine (SVM) is used as a classifier. Both, masses and non-masses, are extracted from the University of South Florida (USF) mammographic image database and are presented to the classifier as crops with pixel size 64 x 64. In order to find the optimal solution to this problem, different featureless crops representations are evaluated. In particular, a pixel-based representation, a Discrete Wavelet Transform (DWT) representation and an Overcomplete Wavelet Transform (OWT) representation are tested.

Abstract
Tipologia del documento
Preprint
Autori
AutoreAffiliazioneORCID
Angelini, Enrico
Campanini, Renato
Iampieri, Emiro
Lanconelli, Nico
Masotti, Matteo
Roffilli, Matteo
Parole chiave
Wavelets, Image Processing, Support Vector Machine, Pattern Classification, Computer-Aided Detection in Mammography
Settori scientifico-disciplinari
DOI
Data di deposito
21 Ott 2004
Ultima modifica
16 Mag 2011 11:37
URI

Altri metadati

Versioni disponibili di questo documento

Statistica sui download

Statistica sui download

Gestione del documento: Visualizza il documento

^